Fal.ai MCP integration
Searches model endpoints, estimates what a run will cost, follows a queued request through its logs, and returns or cancels it on request.
9actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Get queue request result
Lyro retrieves finished AI generation results (images, text, models) to send to customers. Customers see their generated content immediately without manual polling.
Get queue request status with logs
Lyro checks why an AI job failed and retrieves debugging info. Your team fixes broken generations faster by seeing detailed error messages and traces.
Estimate pricing
Lyro tells customers upfront what an AI operation will cost. Customers avoid surprise bills and your team sets accurate expectations before running expensive models.
How businesses use Fal.ai + Lyro
Each card is one request a support team gets, and the Fal.ai actions Lyro runs to close it.
Find the model endpoint that fits the job and its price
Lyro searches fal.ai endpoints by ID, category, or query, expands the OpenAPI schema of a candidate, and returns its unit price and billing unit so the choice is made with the cost visible.
Get ModelsGet Model PricingEstimate PricingReport where a queued generation actually is
Lyro checks a request's status and returns its queue position while it waits or its execution logs once processing starts, with timestamps and severity levels rather than a spinner.
Check Queue Request StatusGet Queue Request Status With LogsStream Request Status UpdatesHand back the finished output or stop a run nobody needs
Once a request reaches COMPLETED, Lyro retrieves its output; if the requirement changed first, it cancels the queued request before processing begins.
Get Queue Request ResultCancel Queue RequestCheck Queue Request StatusVerify a fal.ai webhook before acting on it
Lyro fetches the current ED25519 public key set to check a webhook signature, then confirms the request status and pulls the result the callback is announcing.
Get JWKS for Webhook VerificationCheck Queue Request StatusGet Queue Request Result
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Fal.ai actions it has and picks the ones a request needs.
Connect Fal.ai
Authorize the Fal.ai account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Fal.ai actions that close it and chains as many as the request needs.
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Fal.ai · Lyro
What can you do in Fal.ai without me setting anything up?
These, right away:
- Get jwks for webhook verification
- Cancel queue request
- Estimate pricing
Great, let's start with the first one.
FAQ
Everything else about Fal.ai
Setup, permissions, and the limits of what Lyro can do inside Fal.ai.
No. This toolkit covers model discovery, pricing, queue monitoring, cancellation, and webhook key retrieval - there is no submit or run action on it. Lyro tracks and reports on the generations your own application queues, and returns the output once fal.ai marks the request COMPLETED.
Every action available in Fal.ai
All 9 actions your agent can call on Fal.ai, straight from the live MCP connection.
Cancel queue request
Cancel a queued or in-progress request in fal.ai's queue system.
Estimate pricing
Estimate pricing for fal.ai model endpoints.
Get jwks for webhook verification
Retrieve public keys for webhook signature verification.
Get models
Discover and search fal.ai model endpoints.
Get model pricing
Retrieve unit pricing for model endpoints.
Get queue request result
Retrieve the final result of a completed queue request.
Get queue request status with logs
Retrieve the current status of a queued request with detailed logging information.
Check queue request status
Check the status of a queued request in fal.ai.
Stream request status updates
Stream request status updates via SSE.
The tools Fal.ai sits next to
Same connection, same setup. Pick the next one your team already uses.
Anthropic administrator
Lists the Claude models available on an account, retrieves one by ID, and sends a conversation history for a completion.
Customgpt
Creates agents and attaches sources, reindexes stale pages, reads traffic and conversation analytics, and scores individual answers for accuracy.
Google cloud vision
Runs OCR and image annotation over pictures and PDFs, builds the Product Search catalogue, and polls long-running batch operations.
Metaphor
Fetches the parsed text and metadata for Metaphor documents by ID, several at a time, turning a set of result IDs into readable content.
Rev AI
Submits recordings for transcription, returns transcripts and SRT or VTT captions, and maintains the custom vocabulary behind accuracy.
Tisane
Detects the language of a message, flags abuse types and sentiment, scores text similarity, and paraphrases or translates a passage.
Ready to connect Fal.ai?
Authorize the account and your agent has all 9 actions from the first conversation.